Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases and terms related to correctness and verification in coding or computational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    test consistency and correctness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    principalColumn
    -0.51
     invokingState
    -0.48
    GOTREF
    -0.47
     ProtoMessage
    -0.45
    DockStyle
    -0.44
    \{\\
    -0.42
    uxxxx
    -0.42
     namanya
    -0.42
    MessageWindow
    -0.41
    featureID
    -0.41
    POSITIVE LOGITS
     correct
    0.53
     ביצ
    0.50
     proper
    0.48
     consistency
    0.45
    correct
    0.45
    Correct
    0.44
     accurate
    0.41
    正确的
    0.41
    Спољашње
    0.40
     Correct
    0.40
    Act Density 0.018%

    No Known Activations